Research on Entity Semantic Relation Extraction in Fusion Domain

Entity relationship extraction is one of the important research topics in the field of information extraction, this paper proposes an improved method for extracting entity semantic relations based on tree kernel function, by adding domain knowledge syntax tree and entity semantic information to improve the performance of relation extraction. This method needs to build a domain knowledge tree that reflects the semantic relationship of entities in a particular domain, pruning and denoising the knowledge tree and merging it into the syntax tree to get the domain-specific entity semantic tree. Then, a classification model of entity relationship is constructed to achieve the extraction of domain entity relations. The relationship extraction experiments were conducted on 1500 collected data from tourism domain, the results show that the proposed method is better than the method that does not integrate into the domain knowledge tree. The F value increased by 7.3%.